Rethinking Atrous Convolution for Semantic Image Segmentation

Abstract

In this work, we revisit atrous convolution, a powerful tool to explicitly adjust filter's field-of-view as well as control the resolution of feature responses computed by Deep Convolutional Neural Networks, in the application of semantic image segmentation. To handle the problem of segmenting objects at multiple scales, we design modules which employ atrous convolution in cascade or in parallel to capture multi-scale context by adopting multiple atrous rates. Furthermore, we propose to augment our previously proposed Atrous Spatial Pyramid Pooling module, which probes convolutional features at multiple scales, with image-level features encoding global context and further boost performance. We also elaborate on implementation details and share our experience on training our system. The proposed `DeepLabv3' system significantly improves over our previous DeepLab versions without DenseCRF post-processing and attains comparable performance with other state-of-art models on the PASCAL VOC 2012 semantic image segmentation benchmark.

Add more experimental results

References in corpus (1)

• TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems

Cited by in corpus (964)

• Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
• Res2Net: A New Multi-scale Backbone Architecture
• MobileNetV2: Inverted Residuals and Linear Bottlenecks
• ResUNet-a: a deep learning framework for semantic segmentation of remotely sensed data
• SurfaceNet: Adversarial SVBRDF Estimation from a Single Image
• REFUGE Challenge: A Unified Framework for Evaluating Automated Methods for Glaucoma Assessment from Fundus Photographs
• Medical Image Segmentation Using Deep Learning: A Survey
• COVID-CT-Dataset: A CT Scan Dataset about COVID-19
• High-Resolution Representations for Labeling Pixels and Regions
• The ApolloScape Open Dataset for Autonomous Driving and its Application
• OCNet: Object Context Network for Scene Parsing
• Segmentation Transformer: Object-Contextual Representations for Semantic Segmentation
• Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics
• A Novel Transformer Based Semantic Segmentation Scheme for Fine-Resolution Remote Sensing Images
• Rethinking Pre-training and Self-training
• Mixed supervision for surface-defect detection: from weakly to fully supervised learning
• MVSS-Net: Multi-View Multi-Scale Supervised Networks for Image Manipulation Detection
• Deep High-Resolution Representation Learning for Visual Recognition
• Evolution of Image Segmentation using Deep Convolutional Neural Network: A Survey
• CCNet: Criss-Cross Attention for Semantic Segmentation
• Hierarchical Multi-Scale Attention for Semantic Segmentation
• Coordinate Attention for Efficient Mobile Network Design
• Standardized Assessment of Automatic Segmentation of White Matter Hyperintensities and Results of the WMH Segmentation Challenge
• Split Computing and Early Exiting for Deep Learning Applications: Survey and Research Challenges
• Person Re-identification by Contour Sketch under Moderate Clothing Change
• Uncertainty-aware multi-view co-training for semi-supervised medical image segmentation and domain adaptation
• RANet: Ranking Attention Network for Fast Video Object Segmentation
• Boundary-aware Context Neural Network for Medical Image Segmentation
• Deep Dual-resolution Networks for Real-time and Accurate Semantic Segmentation of Road Scenes
• Modality specific U-Net variants for biomedical image segmentation: A survey
• Radar-Camera Fusion for Object Detection and Semantic Segmentation in Autonomous Driving: A Comprehensive Review
• A Survey on Deep Learning-based Architectures for Semantic Segmentation on 2D images
• Pyramid Attention Network for Semantic Segmentation
• An Empirical Study of Remote Sensing Pretraining
• Contextual Encoder-Decoder Network for Visual Saliency Prediction
• FastFCN: Rethinking Dilated Convolution in the Backbone for Semantic Segmentation
• Adversarial Examples: Attacks and Defenses for Deep Learning
• Object Goal Navigation using Goal-Oriented Semantic Exploration
• DeepGCNs: Making GCNs Go as Deep as CNNs
• Dual Attention Network for Scene Segmentation
• Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers
• K-Net: Towards Unified Image Segmentation
• HED-UNet: Combined Segmentation and Edge Detection for Monitoring the Antarctic Coastline
• A Survey on Deep Learning for Skin Lesion Segmentation
• DABNet: Depth-wise Asymmetric Bottleneck for Real-time Semantic Segmentation
• RGB-T Semantic Segmentation with Location, Activation, and Sharpening
• An Attention-Fused Network for Semantic Segmentation of Very-High-Resolution Remote Sensing Imagery
• SNE-RoadSeg: Incorporating Surface Normal Information into Semantic Segmentation for Accurate Freespace Detection
• Global and Local Contrastive Self-Supervised Learning for Semantic Segmentation of HR Remote Sensing Images
• Auxiliary Tasks in Multi-task Learning
• AxonDeepSeg: automatic axon and myelin segmentation from microscopy data using convolutional neural networks
• Unsupervised Domain Adaptation through Self-Supervision
• CSRNet: Dilated Convolutional Neural Networks for Understanding the Highly Congested Scenes
• Per-Pixel Classification is Not All You Need for Semantic Segmentation
• DeeperLab: Single-Shot Image Parser
• Semi-supervised semantic segmentation needs strong, varied perturbations
• STEm-Seg: Spatio-temporal Embeddings for Instance Segmentation in Videos
• ViTAE: Vision Transformer Advanced by Exploring Intrinsic Inductive Bias
• DetectoRS: Detecting Objects with Recursive Feature Pyramid and Switchable Atrous Convolution
• Affinity Attention Graph Neural Network for Weakly Supervised Semantic Segmentation
• MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer
• Auto-DeepLab: Hierarchical Neural Architecture Search for Semantic Image Segmentation
• Evaluating Bayesian Deep Learning Methods for Semantic Segmentation
• Cascaded Region-based Densely Connected Network for Event Detection: A Seismic Application
• Bag of Tricks for Image Classification with Convolutional Neural Networks
• CNN-based Density Estimation and Crowd Counting: A Survey
• CaraNet: Context Axial Reverse Attention Network for Segmentation of Small Medical Objects
• Improving the Harmony of the Composite Image by Spatial-Separated Attention Module
• X-Net: Brain Stroke Lesion Segmentation Based on Depthwise Separable Convolution and Long-range Dependencies
• Pyramidal Convolution: Rethinking Convolutional Neural Networks for Visual Recognition
• Real-Time Fruit Recognition and Grasping Estimation for Autonomous Apple Harvesting
• Spinal cord gray matter segmentation using deep dilated convolutions
• Learning to Discover Multi-Class Attentional Regions for Multi-Label Image Recognition
• Road Damage Detection Based on Unsupervised Disparity Map Segmentation
• Masked-attention Mask Transformer for Universal Image Segmentation
• Rethinking Space-Time Networks with Improved Memory Coverage for Efficient Video Object Segmentation
• Context Encoding for Semantic Segmentation
• HRFormer: High-Resolution Transformer for Dense Prediction
• BANet: Blur-aware Attention Networks for Dynamic Scene Deblurring
• Recent Progress in Transformer-based Medical Image Analysis
• BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation
• Video-to-Video Synthesis
• Receptive Field Block Net for Accurate and Fast Object Detection
• Micro-Batch Training with Batch-Channel Normalization and Weight Standardization
• Multi-Content Complementation Network for Salient Object Detection in Optical Remote Sensing Images
• Multi-scale fully convolutional neural networks for histopathology image segmentation: from nuclear aberrations to the global tissue architecture
• BiSeNet V2: Bilateral Network with Guided Aggregation for Real-time Semantic Segmentation
• Gated-SCNN: Gated Shape CNNs for Semantic Segmentation
• Dual Graph Convolutional Network for Semantic Segmentation
• Expectation-Maximization Attention Networks for Semantic Segmentation
• Enabling Country-Scale Land Cover Mapping with Meter-Resolution Satellite Imagery
• Light-Weight RefineNet for Real-Time Semantic Segmentation
• Hardware Acceleration of Sparse and Irregular Tensor Computations of ML Models: A Survey and Insights
• DeepGCNs: Can GCNs Go as Deep as CNNs?
• Review: Deep Learning in Electron Microscopy
• FECANet: Boosting Few-Shot Semantic Segmentation with Feature-Enhanced Context-Aware Network
• Automated Evaluation of Semantic Segmentation Robustness for Autonomous Driving
• PointSeg: Real-Time Semantic Segmentation Based on 3D LiDAR Point Cloud
• Data-Free Adversarial Distillation
• PP-LCNet: A Lightweight CPU Convolutional Neural Network
• Cross-Modality Knowledge Distillation Network for Monocular 3D Object Detection
• Real-time High-Resolution Neural Network with Semantic Guidance for Crack Segmentation
• Learning a Discriminative Feature Network for Semantic Segmentation
• Joint Discriminative and Generative Learning for Person Re-identification
• Scale-Aware Trident Networks for Object Detection
• Uncertainty-aware Contrastive Distillation for Incremental Semantic Segmentation
• Topology-Preserving Deep Image Segmentation
• CGNet: A Light-weight Context Guided Network for Semantic Segmentation
• What makes instance discrimination good for transfer learning?
• LiteSeg: A Novel Lightweight ConvNet for Semantic Segmentation
• Stacked Deconvolutional Network for Semantic Segmentation
• SAC-Net: Spatial Attenuation Context for Salient Object Detection
• ADAM Challenge: Detecting Age-related Macular Degeneration from Fundus Images
• Learning Collision-Free Space Detection from Stereo Images: Homography Matrix Brings Better Data Augmentation
• Segmentation in large-scale cellular electron microscopy with deep learning: A literature survey
• Supervised Compression for Resource-Constrained Edge Computing Systems
• T-Net: Nested encoder-decoder architecture for the main vessel segmentation in coronary angiography
• Asymmetric Non-local Neural Networks for Semantic Segmentation
• Lip-reading with Densely Connected Temporal Convolutional Networks
• HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimation
• Efficient and Accurate Arbitrary-Shaped Text Detection with Pixel Aggregation Network
• Unity Perception: Generate Synthetic Data for Computer Vision
• When will the mist clear? On the Interpretability of Machine Learning for Medical Applications: a survey
• Gated-Dilated Networks for Lung Nodule Classification in CT scans
• MudrockNet: Semantic Segmentation of Mudrock SEM Images through Deep Learning
• Weak Supervision for Generating Pixel-Level Annotations in Scene Text Segmentation
• Domain Stylization: A Strong, Simple Baseline for Synthetic to Real Image Domain Adaptation
• Boundary-Aware Segmentation Network for Mobile and Web Applications
• PhenoBench -- A Large Dataset and Benchmarks for Semantic Image Interpretation in the Agricultural Domain
• Axial-DeepLab: Stand-Alone Axial-Attention for Panoptic Segmentation
• Stage-Aware Feature Alignment Network for Real-Time Semantic Segmentation of Street Scenes
• From SLAM to Situational Awareness: Challenges and Survey
• Pyramid Stereo Matching Network
• A Radar Signal Deinterleaving Method Based on Semantic Segmentation with Neural Network
• PathoNet: Deep learning assisted evaluation of Ki-67 and tumor infiltrating lymphocytes (TILs) as prognostic factors in breast cancer; A large dataset and baseline
• KPRNet: Improving projection-based LiDAR semantic segmentation
• Multi-Scale Feature Fusion: Learning Better Semantic Segmentation for Road Pothole Detection
• Panoptic Feature Pyramid Networks
• PaddleSeg: A High-Efficient Development Toolkit for Image Segmentation
• Mapping Informal Settlements in Developing Countries using Machine Learning and Low Resolution Multi-spectral Data
• DFANet: Deep Feature Aggregation for Real-Time Semantic Segmentation
• A Unified Framework for Generalized Low-Shot Medical Image Segmentation with Scarce Data
• ExFuse: Enhancing Feature Fusion for Semantic Segmentation
• Deep Learning Fetal Ultrasound Video Model Match Human Observers in Biometric Measurements
• Gated CRF Loss for Weakly Supervised Semantic Image Segmentation
• Multiscale Deep Equilibrium Models
• Interlaced Sparse Self-Attention for Semantic Segmentation
• Bi-directional Cross-Modality Feature Propagation with Separation-and-Aggregation Gate for RGB-D Semantic Segmentation
• DeepSportradar-v1: Computer Vision Dataset for Sports Understanding with High Quality Annotations
• Video Semantic Segmentation with Distortion-Aware Feature Correction
• A Survey on Deep Learning Methods for Robot Vision
• Inspect, Understand, Overcome: A Survey of Practical Methods for AI Safety
• Development of Skip Connection in Deep Neural Networks for Computer Vision and Medical Image Analysis: A Survey
• Efficient Multi-Task RGB-D Scene Analysis for Indoor Environments
• EPMF: Efficient Perception-aware Multi-sensor Fusion for 3D Semantic Segmentation
• Prior Guided Feature Enrichment Network for Few-Shot Segmentation
• Domain Adaptation for Semantic Segmentation via Class-Balanced Self-Training
• A Survey on State-of-the-art Deep Learning Applications and Challenges
• LatentGNN: Learning Efficient Non-local Relations for Visual Recognition
• CUTIE: Learning to Understand Documents with Convolutional Universal Text Information Extractor
• Global Aggregation then Local Distribution in Fully Convolutional Networks
• CANet: Class-Agnostic Segmentation Networks with Iterative Refinement and Attentive Few-Shot Learning
• ACFNet: Attentional Class Feature Network for Semantic Segmentation
• Real-Time Semantic Segmentation via Multiply Spatial Fusion Network
• AutoGAN: Neural Architecture Search for Generative Adversarial Networks
• Domain Adaptation Meets Zero-Shot Learning: An Annotation-Efficient Approach to Multi-Modality Medical Image Segmentation
• Discriminative out-of-distribution detection for semantic segmentation
• Deep Multi-Branch Aggregation Network for Real-Time Semantic Segmentation in Street Scenes
• MiniSeg: An Extremely Minimum Network for Efficient COVID-19 Segmentation
• Seismic Facies Analysis: A Deep Domain Adaptation Approach
• Strip Pooling: Rethinking Spatial Pooling for Scene Parsing
• A Comprehensive Review of Modern Object Segmentation Approaches
• Attention-guided Chained Context Aggregation for Semantic Segmentation
• Panoptic-DeepLab: A Simple, Strong, and Fast Baseline for Bottom-Up Panoptic Segmentation
• Attention guided global enhancement and local refinement network for semantic segmentation
• A Survey on Continual Semantic Segmentation: Theory, Challenge, Method and Application
• Position, Padding and Predictions: A Deeper Look at Position Information in CNNs
• Hi-UCD: A Large-scale Dataset for Urban Semantic Change Detection in Remote Sensing Imagery
• VoxelNextFusion: A Simple, Unified and Effective Voxel Fusion Framework for Multi-Modal 3D Object Detection
• Component Segmentation of Engineering Drawings Using Graph Convolutional Networks
• Improving Electron Micrograph Signal-to-Noise with an Atrous Convolutional Encoder-Decoder
• Guided Upsampling Network for Real-Time Semantic Segmentation
• Constructing Self-motivated Pyramid Curriculums for Cross-Domain Semantic Segmentation: A Non-Adversarial Approach
• Domain Adaptation for Semantic Segmentation with Maximum Squares Loss
• Learning from Pixel-Level Label Noise: A New Perspective for Semi-Supervised Semantic Segmentation
• Rethinking BiSeNet For Real-time Semantic Segmentation
• Boosting Night-time Scene Parsing with Learnable Frequency
• Bounding Box-Free Instance Segmentation Using Semi-Supervised Learning for Generating a City-Scale Vehicle Dataset
• Relation-Aware Global Attention for Person Re-identification
• Fully Convolutional Networks for Chip-wise Defect Detection Employing Photoluminescence Images
• DRAEM -- A discriminatively trained reconstruction embedding for surface anomaly detection
• Deep Semantic Segmentation at the Edge for Autonomous Navigation in Vineyard Rows
• Learning Depth with Convolutional Spatial Propagation Network
• LDNet: End-to-End Lane Marking Detection Approach Using a Dynamic Vision Sensor
• AP-10K: A Benchmark for Animal Pose Estimation in the Wild
• FEATHER: A Reconfigurable Accelerator with Data Reordering Support for Low-Cost On-Chip Dataflow Switching
• S${}^3$M-Net: Joint Learning of Semantic Segmentation and Stereo Matching for Autonomous Driving
• Road Extraction with Satellite Images and Partial Road Maps
• HS-ResNet: Hierarchical-Split Block on Convolutional Neural Network
• MaskLab: Instance Segmentation by Refining Object Detection with Semantic and Direction Features
• SPGNet: Semantic Prediction Guidance for Scene Parsing
• DeepLab2: A TensorFlow Library for Deep Labeling
• Associatively Segmenting Instances and Semantics in Point Clouds
• Vortex Pooling: Improving Context Representation in Semantic Segmentation
• GFF: Gated Fully Fusion for Semantic Segmentation
• Panoptic Instance Segmentation on Pigs
• Glance-and-Gaze Vision Transformer
• Towards Better Accuracy-efficiency Trade-offs: Divide and Co-training
• AP-MTL: Attention Pruned Multi-task Learning Model for Real-time Instrument Detection and Segmentation in Robot-assisted Surgery
• Reinforced Evolutionary Neural Architecture Search
• Fully Transformer Networks for Semantic Image Segmentation
• Stacked U-Nets: A No-Frills Approach to Natural Image Segmentation
• MaX-DeepLab: End-to-End Panoptic Segmentation with Mask Transformers
• Tiling and Stitching Segmentation Output for Remote Sensing: Basic Challenges and Recommendations
• Learning to Compose Dynamic Tree Structures for Visual Contexts
• PolarNet: An Improved Grid Representation for Online LiDAR Point Clouds Semantic Segmentation
• Feature Fusion for Online Mutual Knowledge Distillation
• OmniPose: A Multi-Scale Framework for Multi-Person Pose Estimation
• BriNet: Towards Bridging the Intra-class and Inter-class Gaps in One-Shot Segmentation
• Inherit with Distillation and Evolve with Contrast: Exploring Class Incremental Semantic Segmentation Without Exemplar Memory
• Lost in Pruning: The Effects of Pruning Neural Networks beyond Test Accuracy
• Exascale Deep Learning for Scientific Inverse Problems
• SSAP: Single-Shot Instance Segmentation With Affinity Pyramid
• Semantic segmentation of mFISH images using convolutional networks
• Unleashing the Power of Contrastive Self-Supervised Visual Models via Contrast-Regularized Fine-Tuning
• Lossless Image Compression through Super-Resolution
• Unsupervised Domain Adaptation in Semantic Segmentation: a Review
• Scaling Wide Residual Networks for Panoptic Segmentation
• FEELVOS: Fast End-to-End Embedding Learning for Video Object Segmentation
• SBSS: Stacking-Based Semantic Segmentation Framework for Very High Resolution Remote Sensing Image
• P2AT: Pyramid Pooling Axial Transformer for Real-time Semantic Segmentation
• RatLesNetv2: A Fully Convolutional Network for Rodent Brain Lesion Segmentation
• Pixel-Anchor: A Fast Oriented Scene Text Detector with Combined Networks
• UNet 3+: A Full-Scale Connected UNet for Medical Image Segmentation
• Efficient Dense Modules of Asymmetric Convolution for Real-Time Semantic Segmentation
• Contrastive Multiview Coding with Electro-optics for SAR Semantic Segmentation
• Hidden Path Selection Network for Semantic Segmentation of Remote Sensing Images
• Iteratively Trained Interactive Segmentation
• Part-aware Prototype Network for Few-shot Semantic Segmentation
• Deep-pretrained-FWI: combining supervised learning with physics-informed neural network
• Instance-level Human Parsing via Part Grouping Network
• Prototype Mixture Models for Few-shot Semantic Segmentation
• Resolution learning in deep convolutional networks using scale-space theory
• Exploiting Shape Cues for Weakly Supervised Semantic Segmentation
• MultiScale Probability Map guided Index Pooling with Attention-based learning for Road and Building Segmentation
• CSC-Unet: A Novel Convolutional Sparse Coding Strategy Based Neural Network for Semantic Segmentation
• Revisiting Locally Supervised Learning: an Alternative to End-to-end Training
• Lucid Data Dreaming for Video Object Segmentation
• RSI-Net: Two-Stream Deep Neural Network for Remote Sensing Imagesbased Semantic Segmentation
• Distribution Alignment: A Unified Framework for Long-tail Visual Recognition
• Attention-based Context Aggregation Network for Monocular Depth Estimation
• Attention-guided Unified Network for Panoptic Segmentation
• An Efficient 3D CNN for Action/Object Segmentation in Video
• Agriculture-Vision: A Large Aerial Image Database for Agricultural Pattern Analysis
• Deep Multiphase Level Set for Scene Parsing
• Regularizing Deep Networks with Semantic Data Augmentation
• Adapting Semantic Segmentation Models for Changes in Illumination and Camera Perspective
• DARTS: DenseUnet-based Automatic Rapid Tool for brain Segmentation
• Prototype Refinement Network for Few-Shot Segmentation
• An efficient solution for semantic segmentation: ShuffleNet V2 with atrous separable convolutions
• Test-time Batch Statistics Calibration for Covariate Shift
• Birds of A Feather Flock Together: Category-Divergence Guidance for Domain Adaptive Segmentation
• ORDNet: Capturing Omni-Range Dependencies for Scene Parsing
• Spatial Pyramid Based Graph Reasoning for Semantic Segmentation
• Mediastinal lymph nodes segmentation using 3D convolutional neural network ensembles and anatomical priors guiding
• Polygonal Building Segmentation by Frame Field Learning
• Squeeze-and-Attention Networks for Semantic Segmentation
• Wisdom of Committees: An Overlooked Approach To Faster and More Accurate Models
• Residual Pyramid Learning for Single-Shot Semantic Segmentation
• DBP: Discrimination Based Block-Level Pruning for Deep Model Acceleration
• DCNAS: Densely Connected Neural Architecture Search for Semantic Image Segmentation
• LEGO: Learning Edge with Geometry all at Once by Watching Videos
• Macroscale fracture surface segmentation via semi-supervised learning considering the structural similarity
• Reliability Does Matter: An End-to-End Weakly Supervised Semantic Segmentation Approach
• Coarse to Fine Multi-Resolution Temporal Convolutional Network
• MUSCLE: Multi-task Self-supervised Continual Learning to Pre-train Deep Models for X-ray Images of Multiple Body Parts
• Delving Deeper into Anti-aliasing in ConvNets
• Automated Characterization of Stenosis in Invasive Coronary Angiography Images with Convolutional Neural Networks
• A Novel Upsampling and Context Convolution for Image Semantic Segmentation
• Temporal-Spatial Feature Pyramid for Video Saliency Detection
• Conquering Data Variations in Resolution: A Slice-Aware Multi-Branch Decoder Network
• Anchor Diffusion for Unsupervised Video Object Segmentation
• WildScenes: A Benchmark for 2D and 3D Semantic Segmentation in Large-scale Natural Environments
• Global Aggregation then Local Distribution for Scene Parsing
• Knowledge Adaptation for Efficient Semantic Segmentation
• Gesture-aware Interactive Machine Teaching with In-situ Object Annotations
• Efficient, high-performance pancreatic segmentation using multi-scale feature extraction
• Unsupervised Light Field Depth Estimation via Multi-view Feature Matching with Occlusion Prediction
• DeepHealth: Review and challenges of artificial intelligence in health informatics
• Selectivity or Invariance: Boundary-aware Salient Object Detection
• CIAN: Cross-Image Affinity Net for Weakly Supervised Semantic Segmentation
• Agile Amulet: Real-Time Salient Object Detection with Contextual Attention
• Continual Coarse-to-Fine Domain Adaptation in Semantic Segmentation
• Revisiting Single Image Depth Estimation: Toward Higher Resolution Maps with Accurate Object Boundaries
• Improving Semantic Segmentation via Decoupled Body and Edge Supervision
• Domain-aware Visual Bias Eliminating for Generalized Zero-Shot Learning
• Label-guided Attention Distillation for Lane Segmentation
• Exploit fully automatic low-level segmented PET data for training high-level deep learning algorithms for the corresponding CT data
• A-NeRF: Articulated Neural Radiance Fields for Learning Human Shape, Appearance, and Pose
• MicroNet: Towards Image Recognition with Extremely Low FLOPs
• Efficient Multi-Task Scene Analysis with RGB-D Transformers
• LOANet: A Lightweight Network Using Object Attention for Extracting Buildings and Roads from UAV Aerial Remote Sensing Images
• Hidden Backdoor Attack against Semantic Segmentation Models
• Unsupervised Continual Semantic Adaptation through Neural Rendering
• Contrastive Syn-to-Real Generalization
• Implicit Ray-Transformers for Multi-view Remote Sensing Image Segmentation
• Joint Semantic Segmentation and Boundary Detection using Iterative Pyramid Contexts
• Joint Iris Segmentation and Localization Using Deep Multi-task Learning Framework
• UPSNet: A Unified Panoptic Segmentation Network
• Benchmarking Neural Radiance Fields for Autonomous Robots: An Overview
• Rethinking Cross-Domain Pedestrian Detection: A Background-Focused Distribution Alignment Framework for Instance-Free One-Stage Detectors
• Exploring Adversarial Robustness of Multi-Sensor Perception Systems in Self Driving
• Active Learning for Deep Detection Neural Networks
• A New Benchmark and Model for Challenging Image Manipulation Detection
• CascadePSP: Toward Class-Agnostic and Very High-Resolution Segmentation via Global and Local Refinement
• Technical Considerations for Semantic Segmentation in MRI using Convolutional Neural Networks
• Structure-Aware Network for Lane Marker Extraction with Dynamic Vision Sensor
• Rethinking Semantic Segmentation Evaluation for Explainability and Model Selection
• Structured Binary Neural Networks for Accurate Image Classification and Semantic Segmentation
• CFPNet-M: A Light-Weight Encoder-Decoder Based Network for Multimodal Biomedical Image Real-Time Segmentation
• Class-wise Dynamic Graph Convolution for Semantic Segmentation
• DRINet++: Efficient Voxel-as-point Point Cloud Segmentation
• LSENet: Location and Seasonality Enhanced Network for Multi-Class Ocean Front Detection
• Hyper-Convolution Networks for Biomedical Image Segmentation
• Flat2Layout: Flat Representation for Estimating Layout of General Room Types
• How Much Can We Really Trust You? Towards Simple, Interpretable Trust Quantification Metrics for Deep Neural Networks
• Semantic Flow for Fast and Accurate Scene Parsing
• Instance-level Few-shot Learning with Class Hierarchy Mining
• Graph-Based Global Reasoning Networks
• CSPN++: Learning Context and Resource Aware Convolutional Spatial Propagation Networks for Depth Completion
• Few-Shot Class-Incremental Learning
• PRSeg: A Lightweight Patch Rotate MLP Decoder for Semantic Segmentation
• IFQA: Interpretable Face Quality Assessment
• MTP: Multi-Task Pruning for Efficient Semantic Segmentation Networks
• AutoOD: Automated Outlier Detection via Curiosity-guided Search and Self-imitation Learning
• Efficient few-shot learning for pixel-precise handwritten document layout analysis
• Learning at a Glance: Towards Interpretable Data-limited Continual Semantic Segmentation via Semantic-Invariance Modelling
• DocScanner: Robust Document Image Rectification with Progressive Learning
• Perturbed and Strict Mean Teachers for Semi-supervised Semantic Segmentation
• ELEV-VISION: Automated Lowest Floor Elevation Estimation from Segmenting Street View Images
• Shape or Texture: Understanding Discriminative Features in CNNs
• Hybrid Multiple Attention Network for Semantic Segmentation in Aerial Images
• Correlation Maximized Structural Similarity Loss for Semantic Segmentation
• C3: Concentrated-Comprehensive Convolution and its application to semantic segmentation
• LeanConvNets: Low-cost Yet Effective Convolutional Neural Networks
• Efficient Differentiable Neural Architecture Search with Meta Kernels
• Label-PEnet: Sequential Label Propagation and Enhancement Networks for Weakly Supervised Instance Segmentation
• Semantic segmentation of longitudinal thermal images for identification of hot and cool spots in urban areas
• Road Damage Detection And Classification In Smartphone Captured Images Using Mask R-CNN
• Anisotropic Convolutional Networks for 3D Semantic Scene Completion
• Real-time CNN-based Segmentation Architecture for Ball Detection in a Single View Setup
• Motion-Appearance Interactive Encoding for Object Segmentation in Unconstrained Videos
• Enhancing sea ice segmentation in Sentinel-1 images with atrous convolutions
• Simpler is Better: Few-shot Semantic Segmentation with Classifier Weight Transformer
• Core Box Image Recognition and its Improvement with a New Augmentation Technique
• Topology-Aware Segmentation Using Discrete Morse Theory
• A White Paper on Neural Network Quantization
• Learning Dynamic Routing for Semantic Segmentation
• Source-Free Domain Adaptation for Semantic Segmentation
• Deep-Energy: Unsupervised Training of Deep Neural Networks
• PolyTransform: Deep Polygon Transformer for Instance Segmentation
• Deep Deterministic Uncertainty for Semantic Segmentation
• Visual Relationship Detection using Scene Graphs: A Survey
• Densely Connected Search Space for More Flexible Neural Architecture Search
• DSNet for Real-Time Driving Scene Semantic Segmentation
• Pose2Seg: Detection Free Human Instance Segmentation
• Multi-Target Domain Adaptation with Collaborative Consistency Learning
• SegFix: Model-Agnostic Boundary Refinement for Segmentation
• OpenRooms: An End-to-End Open Framework for Photorealistic Indoor Scene Datasets
• See More Than Once -- Kernel-Sharing Atrous Convolution for Semantic Segmentation
• Improved Part Segmentation Performance by Optimising Realism of Synthetic Images using Cycle Generative Adversarial Networks
• Efficient 3D Fully Convolutional Networks for Pulmonary Lobe Segmentation in CT Images
• Efficient Segmentation: Learning Downsampling Near Semantic Boundaries
• Panoramic Depth Estimation via Supervised and Unsupervised Learning in Indoor Scenes
• Adaptive Affinity Fields for Semantic Segmentation
• Real-Time High-Performance Semantic Image Segmentation of Urban Street Scenes
• Interactive Deep Refinement Network for Medical Image Segmentation
• Adversarial Image Color Transformations in Explicit Color Filter Space
• Co-Training for Unsupervised Domain Adaptation of Semantic Segmentation Models
• Recurrent U-Net for Resource-Constrained Segmentation
• Low-latency Perception in Off-Road Dynamical Low Visibility Environments
• Customizable Architecture Search for Semantic Segmentation
• Control Distance IoU and Control Distance IoU Loss Function for Better Bounding Box Regression
• Skin Lesion Segmentation Using Atrous Convolution via DeepLab v3
• Learning Uncertainty For Safety-Oriented Semantic Segmentation In Autonomous Driving
• Range Conditioned Dilated Convolutions for Scale Invariant 3D Object Detection
• AdvSPADE: Realistic Unrestricted Attacks for Semantic Segmentation
• Automatic Detection of Interplanetary Coronal Mass Ejections in Solar Wind In Situ Data
• Learning Deep Representations for Semantic Image Parsing: a Comprehensive Overview
• Exploring UMAP in hybrid models of entropy-based and representativeness sampling for active learning in biomedical segmentation
• Naive-Student: Leveraging Semi-Supervised Learning in Video Sequences for Urban Scene Segmentation
• Fully Convolutional Networks for Panoptic Segmentation
• Dynamic Feature Regularized Loss for Weakly Supervised Semantic Segmentation
• Hybridnet for depth estimation and semantic segmentation
• Tensor Low-Rank Reconstruction for Semantic Segmentation
• Double Refinement Network for Efficient Indoor Monocular Depth Estimation
• Real-Time High-Resolution Background Matting
• DenseAttentionSeg: Segment Hands from Interacted Objects Using Depth Input
• Tackling Catastrophic Forgetting and Background Shift in Continual Semantic Segmentation
• Stroke Extraction of Chinese Character Based on Deep Structure Deformable Image Registration
• Generating 3D Bio-Printable Patches Using Wound Segmentation and Reconstruction to Treat Diabetic Foot Ulcers
• SEnSeI: A Deep Learning Module for Creating Sensor Independent Cloud Masks
• Ranking and Tuning Pre-trained Models: A New Paradigm for Exploiting Model Hubs
• Adaptively Connected Neural Networks
• Disentangled Non-Local Neural Networks
• Superpixels and Graph Convolutional Neural Networks for Efficient Detection of Nutrient Deficiency Stress from Aerial Imagery
• Image Augmentation for Multitask Few-Shot Learning: Agricultural Domain Use-Case
• SpatialFlow: Bridging All Tasks for Panoptic Segmentation
• Self-Guided and Cross-Guided Learning for Few-Shot Segmentation
• A High-Efficiency Framework for Constructing Large-Scale Face Parsing Benchmark
• FLOGA: A machine learning ready dataset, a benchmark and a novel deep learning model for burnt area mapping with Sentinel-2
• Linguistic Structure Guided Context Modeling for Referring Image Segmentation
• Rethinking Dilated Convolution for Real-time Semantic Segmentation
• Rethinking Self-Supervised Learning: Small is Beautiful
• Self-supervised blur detection from synthetically blurred scenes
• Affinity LCFCN: Learning to Segment Fish with Weak Supervision
• In Defense of Single-column Networks for Crowd Counting
• PanoNet: Real-time Panoptic Segmentation through Position-Sensitive Feature Embedding
• SegSort: Segmentation by Discriminative Sorting of Segments
• Revisiting Spatial Invariance with Low-Rank Local Connectivity
• Hierarchical Attention Networks for Medical Image Segmentation
• Attentional Ptycho-Tomography (APT) for three-dimensional nanoscale X-ray imaging with minimal data acquisition and computation time
• MSG-Transformer: Exchanging Local Spatial Information by Manipulating Messenger Tokens
• Hard-Attention for Scalable Image Classification
• Deep Affinity Net: Instance Segmentation via Affinity
• Enhancing Cross-task Black-Box Transferability of Adversarial Examples with Dispersion Reduction
• Beyond the Frontier: Predicting Unseen Walls from Occupancy Grids by Learning from Floor Plans
• Evaluation of Data Augmentation and Loss Functions in Semantic Image Segmentation for Drilling Tool Wear Detection
• A Comprehensive Study on Colorectal Polyp Segmentation with ResUNet++, Conditional Random Field and Test-Time Augmentation
• KaliCalib: A Framework for Basketball Court Registration
• Half-Real Half-Fake Distillation for Class-Incremental Semantic Segmentation
• AMD-HookNet for Glacier Front Segmentation
• MSCFNet: A Lightweight Network With Multi-Scale Context Fusion for Real-Time Semantic Segmentation
• Emotion Recognition from Speech
• NuClick: A Deep Learning Framework for Interactive Segmentation of Microscopy Images
• IrisNet: Deep Learning for Automatic and Real-time Tongue Contour Tracking in Ultrasound Video Data using Peripheral Vision
• STEP: Segmenting and Tracking Every Pixel
• Look Before You Leap: Learning Landmark Features for One-Stage Visual Grounding
• Growing Efficient Deep Networks by Structured Continuous Sparsification
• A Lightweight NMS-free Framework for Real-time Visual Fault Detection System of Freight Trains
• GAN- vs. JPEG2000 Image Compression for Distributed Automotive Perception: Higher Peak SNR Does Not Mean Better Semantic Segmentation
• Boosting Semantic Human Matting with Coarse Annotations
• IE-NeRF: Inpainting Enhanced Neural Radiance Fields in the Wild
• Segmenting Objects in Day and Night:Edge-Conditioned CNN for Thermal Image Semantic Segmentation
• Any-Precision Deep Neural Networks
• NL-LinkNet: Toward Lighter but More Accurate Road Extraction with Non-Local Operations
• The Devil is in the Decoder: Classification, Regression and GANs
• Compact Global Descriptor for Neural Networks
• Semantic Segmentation for Partially Occluded Apple Trees Based on Deep Learning
• Instance Localization for Self-supervised Detection Pretraining
• Learning Statistical Texture for Semantic Segmentation
• Disentangled Image Matting
• PointFlow: Flowing Semantics Through Points for Aerial Image Segmentation
• COCO-FUNIT: Few-Shot Unsupervised Image Translation with a Content Conditioned Style Encoder
• AlignSeg: Feature-Aligned Segmentation Networks
• BowNet: Dilated Convolution Neural Network for Ultrasound Tongue Contour Extraction
• FakeMix Augmentation Improves Transparent Object Detection
• Scribble-based Weakly Supervised Deep Learning for Road Surface Extraction from Remote Sensing Images
• Multi-organ Segmentation over Partially Labeled Datasets with Multi-scale Feature Abstraction
• Rethinking Normalization and Elimination Singularity in Neural Networks
• BoundarySqueeze: Image Segmentation as Boundary Squeezing
• Land Cover Change Detection via Semantic Segmentation
• GANHopper: Multi-Hop GAN for Unsupervised Image-to-Image Translation
• A Comprehensive Study on Medical Image Segmentation using Deep Neural Networks
• Encoder Fusion Network with Co-Attention Embedding for Referring Image Segmentation
• ACNN: a Full Resolution DCNN for Medical Image Segmentation
• Multi-Scale Feature Aggregation by Cross-Scale Pixel-to-Region Relation Operation for Semantic Segmentation
• SPCNet:Spatial Preserve and Content-aware Network for Human Pose Estimation
• An Enriched Automated PV Registry: Combining Image Recognition and 3D Building Data
• Decoders Matter for Semantic Segmentation: Data-Dependent Decoding Enables Flexible Feature Aggregation
• DFPENet-geology: A Deep Learning Framework for High Precision Recognition and Segmentation of Co-seismic Landslides
• Learning Spatial Pyramid Attentive Pooling in Image Synthesis and Image-to-Image Translation
• Towards Improving the Consistency, Efficiency, and Flexibility of Differentiable Neural Architecture Search
• PFENet++: Boosting Few-shot Semantic Segmentation with the Noise-filtered Context-aware Prior Mask
• RT-K-Net: Revisiting K-Net for Real-Time Panoptic Segmentation
• Learning Compositional Neural Information Fusion for Human Parsing
• Spatial Attention Pyramid Network for Unsupervised Domain Adaptation
• Adaptive Weighting Multi-Field-of-View CNN for Semantic Segmentation in Pathology
• Prototype-based Incremental Few-Shot Semantic Segmentation
• Deep Convolutional Neural Networks with Spatial Regularization, Volume and Star-shape Priori for Image Segmentation
• AugNet: End-to-End Unsupervised Visual Representation Learning with Image Augmentation
• Global and Local Features through Gaussian Mixture Models on Image Semantic Segmentation
• Learning to Predict Context-adaptive Convolution for Semantic Segmentation
• MEAL: Manifold Embedding-based Active Learning
• Semantic Guided Single Image Reflection Removal
• LRNNet: A Light-Weighted Network with Efficient Reduced Non-Local Operation for Real-Time Semantic Segmentation
• Learning structure-aware semantic segmentation with image-level supervision
• EfficientSeg: An Efficient Semantic Segmentation Network
• Feature Pyramid Transformer
• 3D-DEEP: 3-Dimensional Deep-learning based on elevation patterns forroad scene interpretation
• Analysis of Manual and Automated Skin Tone Assignments for Face Recognition Applications
• Perceptual Extreme Super Resolution Network with Receptive Field Block
• PointAtrousGraph: Deep Hierarchical Encoder-Decoder with Point Atrous Convolution for Unorganized 3D Points
• Dynamic Context Correspondence Network for Semantic Alignment
• Pixel Level Data Augmentation for Semantic Image Segmentation using Generative Adversarial Networks
• GreenScan: Towards large-scale terrestrial monitoring the health of urban trees using mobile sensing
• ST-MTL: Spatio-Temporal Multitask Learning Model to Predict Scanpath While Tracking Instruments in Robotic Surgery
• Human-in-the-loop Extraction of Interpretable Concepts in Deep Learning Models
• Efficient Smoothing of Dilated Convolutions for Image Segmentation
• Semantic Segmentation by Improved Generative Adversarial Networks
• SketchyScene: Richly-Annotated Scene Sketches
• DeLS-3D: Deep Localization and Segmentation with a 3D Semantic Map
• The 1st Agriculture-Vision Challenge: Methods and Results
• Exploring Multi-Branch and High-Level Semantic Networks for Improving Pedestrian Detection
• Cross Branch Feature Fusion Decoder for Consistency Regularization-based Semi-Supervised Change Detection
• Semantic Road Layout Understanding by Generative Adversarial Inpainting
• A Context-and-Spatial Aware Network for Multi-Person Pose Estimation
• Learning of Image Dehazing Models for Segmentation Tasks
• ISP Distillation
• MF-LPR${}^2$: Multi-Frame License Plate Image Restoration and Recognition using Optical Flow
• Vision-Based Uncertainty-Aware Motion Planning based on Probabilistic Semantic Segmentation
• Densely connected multidilated convolutional networks for dense prediction tasks
• DSNet: An Efficient CNN for Road Scene Segmentation
• Densely Dilated Spatial Pooling Convolutional Network using benign loss functions for imbalanced volumetric prostate segmentation
• Graph-guided Architecture Search for Real-time Semantic Segmentation
• Dilated SpineNet for Semantic Segmentation
• DatUS^2: Data-driven Unsupervised Semantic Segmentation with Pre-trained Self-supervised Vision Transformer
• Foreground-Aware Relation Network for Geospatial Object Segmentation in High Spatial Resolution Remote Sensing Imagery
• ScaleNAS: One-Shot Learning of Scale-Aware Representations for Visual Recognition
• Dynamic Neural Representational Decoders for High-Resolution Semantic Segmentation
• BAGS: An automatic homework grading system using the pictures taken by smart phones
• Spatial-Adaptive Network for Single Image Denoising
• D2A U-Net: Automatic Segmentation of COVID-19 Lesions from CT Slices with Dilated Convolution and Dual Attention Mechanism
• Self-Supervised Learning by Estimating Twin Class Distributions
• Predicting Pedestrian Crossing Intention with Feature Fusion and Spatio-Temporal Attention
• Pyramid Network with Online Hard Example Mining for Accurate Left Atrium Segmentation
• A Self-Supervised Feature Map Augmentation (FMA) Loss and Combined Augmentations Finetuning to Efficiently Improve the Robustness of CNNs
• FBC-GAN: Diverse and Flexible Image Synthesis via Foreground-Background Composition
• Deep Fusion of Local and Non-Local Features for Precision Landslide Recognition
• Empirical Study of Multi-Task Hourglass Model for Semantic Segmentation Task
• Regression and Learning with Pixel-wise Attention for Retinal Fundus Glaucoma Segmentation and Detection
• Re-distributing Biased Pseudo Labels for Semi-supervised Semantic Segmentation: A Baseline Investigation
• A Scaling Law for Synthetic-to-Real Transfer: How Much Is Your Pre-training Effective?
• TW-SMNet: Deep Multitask Learning of Tele-Wide Stereo Matching
• Semantic Change Pattern Analysis
• Realtime Global Attention Network for Semantic Segmentation
• DISIR: Deep Image Segmentation with Interactive Refinement
• Distilling Ensemble of Explanations for Weakly-Supervised Pre-Training of Image Segmentation Models
• Generalizing Deep Models for Overhead Image Segmentation Through Getis-Ord Gi* Pooling
• Value of Temporal Dynamics Information in Driving Scene Segmentation
• CaseNet: Content-Adaptive Scale Interaction Networks for Scene Parsing
• Efficient onboard multi-task AI architecture based on self-supervised learning
• QDCNN: Quantum Dilated Convolutional Neural Network
• Learning Debiased and Disentangled Representations for Semantic Segmentation
• Is in-domain data beneficial in transfer learning for landmarks detection in x-ray images?
• All Attention U-NET for Semantic Segmentation of Intracranial Hemorrhages In Head CT Images
• Fast and Accurate Semantic Mapping through Geometric-based Incremental Segmentation
• Are Labels Necessary for Neural Architecture Search?
• Boundary-sensitive Network for Portrait Segmentation
• Parsing Objects at a Finer Granularity: A Survey
• ObjectAug: Object-level Data Augmentation for Semantic Image Segmentation
• Small Obstacle Avoidance Based on RGB-D Semantic Segmentation
• MixSearch: Searching for Domain Generalized Medical Image Segmentation Architectures
• Cooperative Semantic Segmentation and Image Restoration in Adverse Environmental Conditions
• FastFlowNet: A Lightweight Network for Fast Optical Flow Estimation
• Unsupervised domain adaptation via coarse-to-fine feature alignment method using contrastive learning
• Adversarial Examples on Segmentation Models Can be Easy to Transfer
• BusyHands: A Hand-Tool Interaction Database for Assembly Tasks Semantic Segmentation
• 3D-to-2D Distillation for Indoor Scene Parsing
• CTNet: Context-based Tandem Network for Semantic Segmentation
• A Network Structure to Explicitly Reduce Confusion Errors in Semantic Segmentation
• Unifying Neural Learning and Symbolic Reasoning for Spinal Medical Report Generation
• Reversed Active Learning based Atrous DenseNet for Pathological Image Classification
• High Resolution Face Editing with Masked GAN Latent Code Optimization
• Sketch2code: Generating a website from a paper mockup
• CFPNet: Channel-wise Feature Pyramid for Real-Time Semantic Segmentation
• Shape-Texture Debiased Neural Network Training
• Dual-Branch Network with Dual-Sampling Modulated Dice Loss for Hard Exudate Segmentation from Colour Fundus Images
• The 2ST-UNet for Pneumothorax Segmentation in Chest X-Rays using ResNet34 as a Backbone for U-Net
• Multi-scale Attention U-Net (MsAUNet): A Modified U-Net Architecture for Scene Segmentation
• TexMesh: Reconstructing Detailed Human Texture and Geometry from RGB-D Video
• MosAIc: Finding Artistic Connections across Culture with Conditional Image Retrieval
• MRI Pulse Sequence Integration for Deep-Learning Based Brain Metastasis Segmentation
• Learning to Segment Human Body Parts with Synthetically Trained Deep Convolutional Networks
• Recognizing Scenes from Novel Viewpoints
• EdgeSegNet: A Compact Network for Semantic Segmentation
• NeSF: Neural Semantic Fields for Generalizable Semantic Segmentation of 3D Scenes
• Lightweight integration of 3D features to improve 2D image segmentation
• Gradient Information Guided Deraining with A Novel Network and Adversarial Training
• Federated Multi-Target Domain Adaptation
• Spirit Distillation: A Model Compression Method with Multi-domain Knowledge Transfer
• Boosting Few-shot Semantic Segmentation with Transformers
• 3DCFS: Fast and Robust Joint 3D Semantic-Instance Segmentation via Coupled Feature Selection
• GeoSim: Realistic Video Simulation via Geometry-Aware Composition for Self-Driving
• ESNet: An Efficient Symmetric Network for Real-time Semantic Segmentation
• Fast Video Salient Object Detection via Spatiotemporal Knowledge Distillation
• Segmentation of kidney stones in endoscopic video feeds
• DriveGuard: Robustification of Automated Driving Systems with Deep Spatio-Temporal Convolutional Autoencoder
• PSGR: Pixel-wise Sparse Graph Reasoning for COVID-19 Pneumonia Segmentation in CT Images
• Multi-Task Learning for Interpretable Weakly Labelled Sound Event Detection
• A Real Time 1280x720 Object Detection Chip With 585MB/s Memory Traffic
• Semantic Change Detection with Asymmetric Siamese Networks
• Towards Real-Time Automatic Portrait Matting on Mobile Devices
• GuidedMix-Net: Learning to Improve Pseudo Masks Using Labeled Images as Reference
• Feature Binding with Category-Dependant MixUp for Semantic Segmentation and Adversarial Robustness
• Seg-LSTM: Performance of xLSTM for Semantic Segmentation of Remotely Sensed Images
• Neural Architecture Search for Lightweight Non-Local Networks
• MixModule: Mixed CNN Kernel Module for Medical Image Segmentation
• Applications of Deep Learning in Fundus Images: A Review
• Compressing Neural Networks: Towards Determining the Optimal Layer-wise Decomposition
• Learning with Hierarchical Complement Objective
• Boundary Corrected Multi-scale Fusion Network for Real-time Semantic Segmentation
• FNA++: Fast Network Adaptation via Parameter Remapping and Architecture Search
• Ship Instance Segmentation From Remote Sensing Images Using Sequence Local Context Module
• Neural ODEs for Image Segmentation with Level Sets
• A Unified Efficient Pyramid Transformer for Semantic Segmentation
• FlatteNet: A Simple Versatile Framework for Dense Pixelwise Prediction
• Reducing Positional Variance in Cross-sectional Abdominal CT Slices with Deep Conditional Generative Models
• AttaNet: Attention-Augmented Network for Fast and Accurate Scene Parsing
• Improving Semantic Segmentation via Dilated Affinity
• In&Out : Diverse Image Outpainting via GAN Inversion
• Triply Supervised Decoder Networks for Joint Detection and Segmentation
• Multi-view PointNet for 3D Scene Understanding
• Segmentation of Pulmonary Opacification in Chest CT Scans of COVID-19 Patients
• FarSee-Net: Real-Time Semantic Segmentation by Efficient Multi-scale Context Aggregation and Feature Space Super-resolution
• Improving the Resolution of CNN Feature Maps Efficiently with Multisampling
• A deep learning based multiscale approach to segment cancer area in liver whole slide image
• Towards Automatic 3D Shape Instantiation for Deployed Stent Grafts: 2D Multiple-class and Class-imbalance Marker Segmentation with Equally-weighted Focal U-Net
• Generalizable Model-agnostic Semantic Segmentation via Target-specific Normalization
• One-Vote Veto: Semi-Supervised Learning for Low-Shot Glaucoma Diagnosis
• Learning Discriminative Feature with CRF for Unsupervised Video Object Segmentation
• DivergentNets: Medical Image Segmentation by Network Ensemble
• Consensus Feature Network for Scene Parsing
• A Location-Sensitive Local Prototype Network for Few-Shot Medical Image Segmentation
• Pavement Distress Detection and Segmentation using YOLOv4 and DeepLabv3 on Pavements in the Philippines
• Occlusion-shared and Feature-separated Network for Occlusion Relationship Reasoning
• Boosted GAN with Semantically Interpretable Information for Image Inpainting
• Learning a Domain-Agnostic Visual Representation for Autonomous Driving via Contrastive Loss
• SynthRef: Generation of Synthetic Referring Expressions for Object Segmentation
• Contextual Information Enhanced Convolutional Neural Networks for Retinal Vessel Segmentation in Color Fundus Images
• Distance Guided Channel Weighting for Semantic Segmentation
• Dilated Convolutions with Lateral Inhibitions for Semantic Image Segmentation
• Beyond Self-Supervision: A Simple Yet Effective Network Distillation Alternative to Improve Backbones
• Self-Supervised Tuning for Few-Shot Segmentation
• Sparse-to-dense Feature Matching: Intra and Inter domain Cross-modal Learning in Domain Adaptation for 3D Semantic Segmentation
• A New Local Transformation Module for Few-shot Segmentation
• Structure-aware Person Image Generation with Pose Decomposition and Semantic Correlation
• TreeSegNet: Adaptive Tree CNNs for Subdecimeter Aerial Image Segmentation
• Quantized Convolutional Neural Networks Through the Lens of Partial Differential Equations
• ShelfNet for Fast Semantic Segmentation
• Ancient Painting to Natural Image: A New Solution for Painting Processing
• DADA-2000: Can Driving Accident be Predicted by Driver Attention? Analyzed by A Benchmark
• Continual Unsupervised Domain Adaptation for Semantic Segmentation
• See More, Know More: Unsupervised Video Object Segmentation with Co-Attention Siamese Networks
• Semi-Global Shape-aware Network
• Enhanced Self-Perception in Mixed Reality: Egocentric Arm Segmentation and Database with Automatic Labelling
• Auto-Annotation Quality Prediction for Semi-Supervised Learning with Ensembles
• A Multi-task Contextual Atrous Residual Network for Brain Tumor Detection & Segmentation
• Spatial Shortcut Network for Human Pose Estimation
• I2CKD : Intra- and Inter-Class Knowledge Distillation for Semantic Segmentation
• Real-Time Freespace Segmentation on Autonomous Robots for Detection of Obstacles and Drop-Offs
• Partial Graph Reasoning for Neural Network Regularization
• HybridNetSeg: A Compact Hybrid Network for Retinal Vessel Segmentation
• Deep Dual Pyramid Network for Barcode Segmentation using Barcode-30k Database
• SA${}^2$Net: Scale-Adaptive Structure-Affinity Transformation for Spine Segmentation from Ultrasound Volume Projection Imaging
• LOD1 3D City Model from LiDAR: The Impact of Segmentation Accuracy on Quality of Urban 3D Modeling and Morphology Extraction
• Computer vision for liquid samples in hospitals and medical labs using hierarchical image segmentation and relations prediction
• Effective Data Fusion with Generalized Vegetation Index: Evidence from Land Cover Segmentation in Agriculture
• Edge-Guided Occlusion Fading Reduction for a Light-Weighted Self-Supervised Monocular Depth Estimation
• One-Shot Weakly Supervised Video Object Segmentation
• SIGN: Spatial-information Incorporated Generative Network for Generalized Zero-shot Semantic Segmentation
• FaceShapeGene: A Disentangled Shape Representation for Flexible Face Image Editing
• An Evaluation of RGB and LiDAR Fusion for Semantic Segmentation
• AttendSeg: A Tiny Attention Condenser Neural Network for Semantic Segmentation on the Edge
• ExplainFix: Explainable Spatially Fixed Deep Networks
• Direct Object Recognition Without Line-of-Sight Using Optical Coherence
• ACE-Net: Biomedical Image Segmentation with Augmented Contracting and Expansive Paths
• TriangleNet: Edge Prior Augmented Network for Semantic Segmentation through Cross-Task Consistency
• Spatial-Aware Non-Local Attention for Fashion Landmark Detection
• Referring Image Segmentation via Cross-Modal Progressive Comprehension
• Bipartite Conditional Random Fields for Panoptic Segmentation
• Hard Pixel Mining for Depth Privileged Semantic Segmentation
• Fractal Pyramid Networks
• See Clearer at Night: Towards Robust Nighttime Semantic Segmentation through Day-Night Image Conversion
• Learning Fully Dense Neural Networks for Image Semantic Segmentation
• The Application of Deep Learning for Lymph Node Segmentation: A Systematic Review
• Adaptive Context Encoding Module for Semantic Segmentation
• OVSNet : Towards One-Pass Real-Time Video Object Segmentation
• High Frequency Residual Learning for Multi-Scale Image Classification
• Automatic Labeled LiDAR Data Generation based on Precise Human Model
• Highly Efficient Follicular Segmentation in Thyroid Cytopathological Whole Slide Image
• High-Order Paired-ASPP Networks for Semantic Segmenation
• Zero-Shot Video Object Segmentation via Attentive Graph Neural Networks
• Single Image Depth Estimation Trained via Depth from Defocus Cues
• Handling Missing MRI Input Data in Deep Learning Segmentation of Brain Metastases: A Multi-Center Study
• AnoNet: Weakly Supervised Anomaly Detection in Textured Surfaces
• SINet: Extreme Lightweight Portrait Segmentation Networks with Spatial Squeeze Modules and Information Blocking Decoder
• Distilling Pixel-Wise Feature Similarities for Semantic Segmentation
• PT-ResNet: Perspective Transformation-Based Residual Network for Semantic Road Image Segmentation
• Defective samples simulation through Neural Style Transfer for automatic surface defect segment
• 3D Neighborhood Convolution: Learning Depth-Aware Features for RGB-D and RGB Semantic Segmentation
• Automatic Lumbar Spinal CT Image Segmentation with a Dual Densely Connected U-Net
• Renovating Parsing R-CNN for Accurate Multiple Human Parsing
• EfficientFCN: Holistically-guided Decoding for Semantic Segmentation
• Representative Graph Neural Network
• Fast Video Object Segmentation With Temporal Aggregation Network and Dynamic Template Matching
• Deep Learning of Unified Region, Edge, and Contour Models for Automated Image Segmentation
• Segmentation task for fashion and apparel
• Uncertainty Estimation in Deep 2D Echocardiography Segmentation
• Application of Computer Vision and Machine Learning for Digitized Herbarium Specimens: A Systematic Literature Review
• Spirit Distillation: Precise Real-time Semantic Segmentation of Road Scenes with Insufficient Data
• Shapley Explanation Networks
• Efficient sign language recognition system and dataset creation method based on deep learning and image processing
• Deep Consensus Learning
• CXR-Net: An Artificial Intelligence Pipeline for Quick Covid-19 Screening of Chest X-Rays
• Graphonomy: Universal Image Parsing via Graph Reasoning and Transfer
• GridTracer: Automatic Mapping of Power Grids using Deep Learning and Overhead Imagery
• Two-phase Pseudo Label Densification for Self-training based Domain Adaptation
• MUSCLE: Strengthening Semi-Supervised Learning Via Concurrent Unsupervised Learning Using Mutual Information Maximization
• Rethinking Text Segmentation: A Novel Dataset and A Text-Specific Refinement Approach
• Automatic Recognition of the Supraspinatus Tendinopathy from Ultrasound Images using Convolutional Neural Networks
• Lung Segmentation in Chest X-rays with Res-CR-Net
• HDR-cGAN: Single LDR to HDR Image Translation using Conditional GAN
• Normal Learning in Videos with Attention Prototype Network
• Pi-NAS: Improving Neural Architecture Search by Reducing Supernet Training Consistency Shift
• FaPN: Feature-aligned Pyramid Network for Dense Image Prediction
• Learning Meta-class Memory for Few-Shot Semantic Segmentation
• LabOR: Labeling Only if Required for Domain Adaptive Semantic Segmentation
• Attention-based fusion of semantic boundary and non-boundary information to improve semantic segmentation
• Real-time Keypoints Detection for Autonomous Recovery of the Unmanned Ground Vehicle
• Adaptive Dilated Convolution For Human Pose Estimation
• DynaDog+T: A Parametric Animal Model for Synthetic Canine Image Generation
• AlterSGD: Finding Flat Minima for Continual Learning by Alternative Training
• ICDAR 2021 Competition on Components Segmentation Task of Document Photos
• FPCD: An Open Aerial VHR Dataset for Farm Pond Change Detection
• Comparison of Cross-Entropy, Dice, and Focal Loss for Sea Ice Type Segmentation
• Confident Naturalness Explanation (CNE): A Framework to Explain and Assess Patterns Forming Naturalness
• Ensemble Methods for Multi-Organ Segmentation in CT Series
• Comparing Adversarial and Supervised Learning for Organs at Risk Segmentation in CT images
• The Devil is in the Margin: Margin-based Label Smoothing for Network Calibration
• Cerberus Transformer: Joint Semantic, Affordance and Attribute Parsing
• Learning Class-Agnostic Pseudo Mask Generation for Box-Supervised Semantic Segmentation
• Neural Architecture Search with Random Labels
• Inception Convolution with Efficient Dilation Search
• Efficient Scale-Permuted Backbone with Learned Resource Distribution
• Real-time Localized Photorealistic Video Style Transfer
• An Exploration of Target-Conditioned Segmentation Methods for Visual Object Trackers
• GIMP-ML: Python Plugins for using Computer Vision Models in GIMP
• Alleviating Semantic-level Shift: A Semi-supervised Domain Adaptation Method for Semantic Segmentation
• Who2com: Collaborative Perception via Learnable Handshake Communication
• End-to-End Face Parsing via Interlinked Convolutional Neural Networks
• Random Bundle: Brain Metastases Segmentation Ensembling through Annotation Randomization
• Feedbackward Decoding for Semantic Segmentation
• Image Harmonization Dataset iHarmony4: HCOCO, HAdobe5k, HFlickr, and Hday2night
• A Novel Deep Learning Based Approach for Left Ventricle Segmentation in Echocardiography: MFP-Unet
• Generative-Discriminative Complementary Learning
• Multi${}^3$Net: Segmenting Flooded Buildings via Fusion of Multiresolution, Multisensor, and Multitemporal Satellite Imagery
• ELASTIC: Improving CNNs with Dynamic Scaling Policies
• Parsing R-CNN for Instance-Level Human Analysis
• Adaptive Temporal Encoding Network for Video Instance-level Human Parsing
• Weakly- and Semi-Supervised Panoptic Segmentation
• Dilated Temporal Relational Adversarial Network for Generic Video Summarization
• Dynamic Video Segmentation Network
• One-Shot Segmentation in Clutter
• Spatially-Adaptive Filter Units for Deep Neural Networks
• Semantic-guided Automatic Natural Image Matting with Trimap Generation Network and Light-weight Non-local Attention
• Multimodal Knowledge Expansion
• 3D Guided Weakly Supervised Semantic Segmentation
• Cirrus: A Long-range Bi-pattern LiDAR Dataset
• GANSeg: Learning to Segment by Unsupervised Hierarchical Image Generation
• Towards Recognizing New Semantic Concepts in New Visual Domains
• A Holistically-Guided Decoder for Deep Representation Learning with Applications to Semantic Segmentation and Object Detection
• Global Context Networks
• Towards Understanding the Effectiveness of Attention Mechanism
• Probabilistic Attention for Interactive Segmentation
• Bidirectional Multi-scale Attention Networks for Semantic Segmentation of Oblique UAV Imagery
• HUGE2: a Highly Untangled Generative-model Engine for Edge-computing
• Explainability in CNN Models By Means of Z-Scores
• Integrating Multiple Receptive Fields through Grouped Active Convolution
• Open-World Entity Segmentation
• PECNet: A Deep Multi-Label Segmentation Network for Eosinophilic Esophagitis Biopsy Diagnostics
• Exposing Semantic Segmentation Failures via Maximum Discrepancy Competition
• One-Shot Medical Landmark Detection
• Zero-shot Adversarial Quantization
• Interflow: Aggregating Multi-layer Feature Mappings with Attention Mechanism
• Multi-Level Contextual Network for Biomedical Image Segmentation
• TerrainMesh: Metric-Semantic Terrain Reconstruction from Aerial Images Using Joint 2D-3D Learning
• Boundary Knowledge Translation based Reference Semantic Segmentation
• Adversarial Learning for Image Forensics Deep Matching with Atrous Convolution
• DCANet: Dense Context-Aware Network for Semantic Segmentation
• Edge-competing Pathological Liver Vessel Segmentation with Limited Labels
• Implicit Integration of Superpixel Segmentation into Fully Convolutional Networks
• MACNet: Multi-scale Atrous Convolution Networks for Food Places Classification in Egocentric Photo-streams
• ESFNet: Efficient Network for Building Extraction from High-Resolution Aerial Images
• "BNN - BN = ?": Training Binary Neural Networks without Batch Normalization
• iSPA-Net: Iterative Semantic Pose Alignment Network
• Semantic Image Matting
• Framework-agnostic Semantically-aware Global Reasoning for Segmentation
• GlassNet: Label Decoupling-based Three-stream Neural Network for Robust Image Glass Detection
• Focusing on Shadows for Predicting Heightmaps from Single Remotely Sensed RGB Images with Deep Learning
• torchdistill Meets Hugging Face Libraries for Reproducible, Coding-Free Deep Learning Studies: A Case Study on NLP
• Context Prior for Scene Segmentation
• FAIRS -- Soft Focus Generator and Attention for Robust Object Segmentation from Extreme Points
• Surveilling Surveillance: Estimating the Prevalence of Surveillance Cameras with Street View Data
• Probabilistic Semantic Segmentation Refinement by Monte Carlo Region Growing
• Semantic Segmentation and Object Detection Towards Instance Segmentation: Breast Tumor Identification
• Feature boosting with efficient attention for scene parsing
• MSDU-net: A Multi-Scale Dilated U-net for Blur Detection
• Convolutional neural networks compression with low rank and sparse tensor decompositions
• Stitching for Neuroevolution: Recombining Deep Neural Networks without Breaking Them
• Realtime Rooftop Landing Site Identification and Selection in Urban City Simulation
• An EM Framework for Online Incremental Learning of Semantic Segmentation
• Improving Lesion Segmentation in Medical Images by Global and Regional Feature Compensation
• Combining Semantic Guidance and Deep Reinforcement Learning For Generating Human Level Paintings
• SkyScapes -- Fine-Grained Semantic Understanding of Aerial Scenes
• Model Compression for Resource-Constrained Mobile Robots
• Retrieval and Localization with Observation Constraints
• Monocular Outdoor Semantic Mapping with a Multi-task Network
• Discover the Mysteries of the Maya: Selected Contributions from the Machine Learning Challenge & The Discovery Challenge Workshop at ECML PKDD 2021
• MI^2GAN: Generative Adversarial Network for Medical Image Domain Adaptation using Mutual Information Constraint
• Deep Neural Network for 3D Surface Segmentation based on Contour Tree Hierarchy
• TBN-ViT: Temporal Bilateral Network with Vision Transformer for Video Scene Parsing
• Noise Reduction Technique for Raman Spectrum using Deep Learning Network
• SoFAr: Shortcut-based Fractal Architectures for Binary Convolutional Neural Networks
• GINet: Graph Interaction Network for Scene Parsing
• Cross-Modal Progressive Comprehension for Referring Segmentation
• Multi Receptive Field Network for Semantic Segmentation
• Real time backbone for semantic segmentation
• DT-Net: A novel network based on multi-directional integrated convolution and threshold convolution
• Light Field Saliency Detection with Dual Local Graph Learning andReciprocative Guidance
• RefVOS: A Closer Look at Referring Expressions for Video Object Segmentation
• CDGNet: Class Distribution Guided Network for Human Parsing
• Adaptive Image Transformations for Transfer-based Adversarial Attack
• Semantic Feature Attention Network for Liver Tumor Segmentation in Large-scale CT database
• Adaptive Context Network for Scene Parsing
• Location-aware Upsampling for Semantic Segmentation
• TridentAdapt: Learning Domain-invariance via Source-Target Confrontation and Self-induced Cross-domain Augmentation
• Scaling Matters in Deep Structured-Prediction Models
• Localized Super Resolution for Foreground Images using U-Net and MR-CNN
• Graph-FCN for image semantic segmentation
• UltraPose: Synthesizing Dense Pose with 1 Billion Points by Human-body Decoupling 3D Model
• Dense Prediction with Attentive Feature Aggregation
• Semantically Robust Unpaired Image Translation for Data with Unmatched Semantics Statistics
• Brain Metastasis Segmentation Network Trained with Robustness to Annotations with Multiple False Negatives
• CARPAL: Confidence-Aware Intent Recognition for Parallel Autonomy
• High resolution weakly supervised localization architectures for medical images
• Data-free Knowledge Distillation for Segmentation using Data-Enriching GAN
• Semantic-Aware Contrastive Learning for Multi-object Medical Image Segmentation
• Task-driven Semantic Coding via Reinforcement Learning
• Fastidious Attention Network for Navel Orange Segmentation
• Real-Time Semantic Segmentation via Auto Depth, Downsampling Joint Decision and Feature Aggregation
• EgoReID Dataset: Person Re-identification in Videos Acquired by Mobile Devices with First-Person Point-of-View
• Multigrid-in-Channels Architectures for Wide Convolutional Neural Networks
• Real-Time Uncertainty Estimation in Computer Vision via Uncertainty-Aware Distribution Distillation
• One to Transfer All: A Universal Transfer Framework for Vision Foundation Model with Few Data
• Cycle-consistent Generative Adversarial Networks for Neural Style Transfer using data from Chang'E-4
• Batch Normalization with Enhanced Linear Transformation
• Recognizing Object Affordances to Support Scene Reasoning for Manipulation Tasks
• What Synthesis is Missing: Depth Adaptation Integrated with Weak Supervision for Indoor Scene Parsing
• Depth-Adapted CNN for RGB-D cameras
• Implicit Label Augmentation on Partially Annotated Clips via Temporally-Adaptive Features Learning
• ELKPPNet: An Edge-aware Neural Network with Large Kernel Pyramid Pooling for Learning Discriminative Features in Semantic Segmentation
• CNN-based Semantic Segmentation using Level Set Loss
• Sequential image processing methods for improving semantic video segmentation algorithms
• Differentiating Features for Scene Segmentation Based on Dedicated Attention Mechanisms
• Inspect Transfer Learning Architecture with Dilated Convolution
• End-to-end Training of CNN-CRF via Differentiable Dual-Decomposition
• News Cover Assessment via Multi-task Learning
• Multi-Scale Weight Sharing Network for Image Recognition
• Robust Brain Magnetic Resonance Image Segmentation for Hydrocephalus Patients: Hard and Soft Attention
• Multilayer Dense Connections for Hierarchical Concept Classification
• Realizing Pixel-Level Semantic Learning in Complex Driving Scenes based on Only One Annotated Pixel per Class
• BiCANet: Bi-directional Contextual Aggregating Network for Image Semantic Segmentation
• Deep Grouping Model for Unified Perceptual Parsing
• Temporal Accumulative Features for Sign Language Recognition
• LORCK: Learnable Object-Resembling Convolution Kernels
• ARMA Nets: Expanding Receptive Field for Dense Prediction
• Matrix Engines for High Performance Computing:A Paragon of Performance or Grasping at Straws?
• RGB-based Semantic Segmentation Using Self-Supervised Depth Pre-Training
• Rethinking Fully Convolutional Networks for the Analysis of Photoluminescence Wafer Images
• Neural Bootstrapper
• Noisy-LSTM: Improving Temporal Awareness for Video Semantic Segmentation
• HCNet: Hierarchical Context Network for Semantic Segmentation
• Dense Dual-Path Network for Real-time Semantic Segmentation
• Weakly Supervised Instance Segmentation by Deep Community Learning
• An Abstraction Model for Semantic Segmentation Algorithms
• Regularizing Explanations in Bayesian Convolutional Neural Networks
• Machine Vision for Improved Human-Robot Cooperation in Adverse Underwater Conditions
• Video Class Agnostic Segmentation with Contrastive Learning for Autonomous Driving
• ReflectNet -- A Generative Adversarial Method for Single Image Reflection Suppression
• SauvolaNet: Learning Adaptive Sauvola Network for Degraded Document Binarization
• SpaceMeshLab: Spatial Context Memoization and Meshgrid Atrous Convolution Consensus for Semantic Segmentation
• PAENet: A Progressive Attention-Enhanced Network for 3D to 2D Retinal Vessel Segmentation
• AASeg: Attention Aware Network for Real Time Semantic Segmentation
• HPTQ: Hardware-Friendly Post Training Quantization
• Predicting 3D shapes, masks, and properties of materials, liquids, and objects inside transparent containers, using the TransProteus CGI dataset
• Searching for TrioNet: Combining Convolution with Local and Global Self-Attention
• Weakly-supervised fire segmentation by visualizing intermediate CNN layers
• A Dense Tensor Accelerator with Data Exchange Mesh for DNN and Vision Workloads
• Anomaly-Aware Semantic Segmentation by Leveraging Synthetic-Unknown Data
• Trimap-guided Feature Mining and Fusion Network for Natural Image Matting
• A Robust Billboard-based Free-viewpoint Video Synthesizing Algorithm for Sports Scenes
• Learning Rich Representations For Structured Visual Prediction Tasks
• DV3+HED+: A DCNNs-based Framework to Monitor Temporary Works and ESAs in Railway Construction Project Using VHR Satellite Images
• OCELOT 2023: Cell Detection from Cell-Tissue Interaction Challenge
• Voxel-level Siamese Representation Learning for Abdominal Multi-Organ Segmentation
• Towards a Sample Efficient Reinforcement Learning Pipeline for Vision Based Robotics
• A Distraction Score for Watermarks
• VS-Net: Voting with Segmentation for Visual Localization
• Dedge-AGMNet:an effective stereo matching network optimized by depth edge auxiliary task
• Dynamic Dual Sampling Module for Fine-Grained Semantic Segmentation
• Unsupervised Adaptive Semantic Segmentation with Local Lipschitz Constraint
• CMF: Cascaded Multi-model Fusion for Referring Image Segmentation
• Domain Consistency Regularization for Unsupervised Multi-source Domain Adaptive Classification
• Building Intelligent Autonomous Navigation Agents
• A Comparative Study of High-Recall Real-Time Semantic Segmentation Based on Swift Factorized Network
• Cross Attention Network for Semantic Segmentation
• A new smart-cropping pipeline for prostate segmentation using deep learning networks
• Log-Polar Space Convolution for Convolutional Neural Networks
• MaskPlus: Improving Mask Generation for Instance Segmentation
• Visual Boundary Knowledge Translation for Foreground Segmentation
• From augmented microscopy to the topological transformer: a new approach in cell image analysis for Alzheimer's research
• Global and Local Texture Randomization for Synthetic-to-Real Semantic Segmentation
• Region Refinement Network for Salient Object Detection
• Stereo Waterdrop Removal with Row-wise Dilated Attention
• One-Shot Object Affordance Detection in the Wild
• Boundary-aware Graph Reasoning for Semantic Segmentation
• COVID-view: Diagnosis of COVID-19 using Chest CT
• Learning Deep Multimodal Feature Representation with Asymmetric Multi-layer Fusion
• Detecting and Segmenting Adversarial Graphics Patterns from Images
• Sparse Spatial Attention Network for Semantic Segmentation
• Automatic Portrait Video Matting via Context Motion Network
• Neural Architecture Search in operational context: a remote sensing case-study
• PDFNet: Pointwise Dense Flow Network for Urban-Scene Segmentation
• SparseMask: Differentiable Connectivity Learning for Dense Image Prediction
• MetaPix: Domain Transfer for Semantic Segmentation by Meta Pixel Weighting
• Semantic Segmentation for Urban-Scene Images
• Reimagine BiSeNet for Real-Time Domain Adaptation in Semantic Segmentation
• Learned Image Compression for Machine Perception
• Covariance Self-Attention Dual Path UNet for Rectal Tumor Segmentation
• Learning Super-resolution 3D Segmentation of Plant Root MRI Images from Few Examples
• Fast Object Detection with Latticed Multi-Scale Feature Fusion
• TB-Net: A Three-Stream Boundary-Aware Network for Fine-Grained Pavement Disease Segmentation
• We don't Need Thousand Proposals$:$ Single Shot Actor-Action Detection in Videos
• Segmentation of Objects by Hashing
• Vulcan Centaur: towards end-to-end real-time perception in lunar rovers
• Affinity Derivation and Graph Merge for Instance Segmentation
• A Dark Flash Normal Camera
• RethNet: Object-by-Object Learning for Detecting Facial Skin Problems
• A Novel Technique for Evidence based Conditional Inference in Deep Neural Networks via Latent Feature Perturbation
• L-SNet: from Region Localization to Scale Invariant Medical Image Segmentation
• Shape-Tailored Deep Neural Networks
• Linear Semantics in Generative Adversarial Networks
• High-quality Low-dose CT Reconstruction Using Convolutional Neural Networks with Spatial and Channel Squeeze and Excitation
• Hierarchical Pyramid Representations for Semantic Segmentation
• Weakly Supervised Video Salient Object Detection
• Dewarping Document Image By Displacement Flow Estimation with Fully Convolutional Network
• A De-raining semantic segmentation network for real-time foreground segmentation
• Multi-Scale Dual-Branch Fully Convolutional Network for Hand Parsing
• Improving Shape Deformation in Unsupervised Image-to-Image Translation
• Learning-based super interpolation and extrapolation for speckled image reconstruction
• Unsupervised segmentation via semantic-apparent feature fusion
• Bounding Box Embedding for Single Shot Person Instance Segmentation
• Domain Adaptation with Morphologic Segmentation
• Sequential Feature Filtering Classifier
• A lateral semicircular canal segmentation based geometric calibration for human temporal bone CT Image
• GSTO: Gated Scale-Transfer Operation for Multi-Scale Feature Learning in Pixel Labeling
• PGD-UNet: A Position-Guided Deformable Network for Simultaneous Segmentation of Organs and Tumors
• ContourRend: A Segmentation Method for Improving Contours by Rendering
• Malleable 2.5D Convolution: Learning Receptive Fields along the Depth-axis for RGB-D Scene Parsing
• Crowdsampling the Plenoptic Function
• Adversarial Structure Matching for Structured Prediction Tasks
• RoIFusion: 3D Object Detection from LiDAR and Vision
• Angular Luminance for Material Segmentation